Watermark Basins: Black-Box Detection of Distilled LLMs
Read the original on arXiv Computation and Language →The paper introduces Watermark Basin Alignment (WM‑Basin), a black‑box method for detecting distilled large language models (LLMs). It exploits a persistent watermark basin—a key‑specific geometric signal embedded in the teacher’s parameter space during fine‑tuning—that remains detectable even when token‑level signals vanish. WM‑Basin maps suspect model outputs to gradient representations, removes ordinary fine‑tuning directions, and tests alignment with the watermark basin, achieving significantly higher detection rates than token‑level baselines across a range of teacher and student models.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.